Timezone: »
The recent availability of Electronic Health Records (EHR) has allowed for the development of algorithms predicting inpatient risk of deterioration and trajectory evolution. However, prediction of disease progression with EHR is challenging since these data are sparse, heterogeneous, multi-dimensional, and multi-modal time-series. As such, clustering is regularly used to identify similar groups within the patient cohort to improve prediction. Current models have shown some success in obtaining cluster representations of patient trajectories. However, they i) fail to obtain clinical interpretability for each cluster, and ii) struggle to learn meaningful cluster numbers in the context of imbalanced distribution of disease outcomes. We propose a supervised deep learning model to cluster EHR data based on the identification of clinically understandable phenotypes with regard to both outcome prediction and patient trajectory. We introduce novel loss functions to address the problems of class imbalance and cluster collapse, and furthermore propose a feature-time attention mechanism to identify cluster-based phenotype importance across time and feature dimensions. We tested our model in two datasets corresponding to distinct medical settings. Our model yielded added interpretability to cluster formation and outperformed benchmarks by at least 4% in relevant metrics.
Author Information
Henrique Aguiar (University of Oxford)
Mauro Santos (University of Oxford)
Peter Watkinson (Oxford University Hospitals NHS Foundation Trust)
Tingting Zhu (University of Oxford)
Related Events (a corresponding poster, oral, or spotlight)
-
2022 Spotlight: Learning of Cluster-based Feature Importance for Electronic Health Record Time-series »
Thu. Jul 21st 06:00 -- 06:05 PM Room Hall G
More from the Same Authors
-
2022 Workshop: The 1st Workshop on Healthcare AI and COVID-19 »
Peng Xu · Tingting Zhu · Pengkai Zhu · Tianrui Chen · David Clifton · Danielle Belgrave · Yuanting Zhang -
2022 Poster: SoQal: Selective Oracle Questioning for Consistency Based Active Learning of Cardiac Signals »
Dani Kiyasseh · Tingting Zhu · David Clifton -
2022 Spotlight: SoQal: Selective Oracle Questioning for Consistency Based Active Learning of Cardiac Signals »
Dani Kiyasseh · Tingting Zhu · David Clifton -
2021 Poster: CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients »
Dani Kiyasseh · Tingting Zhu · David Clifton -
2021 Spotlight: CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients »
Dani Kiyasseh · Tingting Zhu · David Clifton -
2020 Poster: Student-Teacher Curriculum Learning via Reinforcement Learning: Predicting Hospital Inpatient Admission Location »
Rasheed El-Bouri · David Eyre · Peter Watkinson · Tingting Zhu · David Clifton